L₁-norm loss based twin support vector machine for data recognition

详细信息    查看全文

• 作者：Xinjun Peng ; ^a ; ^b ; ^{xjpeng@shnu.edu.cn" class="auth_mail" title="E-mail the corresponding author} ; ^{xjpeng999@gmail.com" class="auth_mail" title="E-mail the corresponding author} ; Dong Xu^a ; Lingyan Kong^a ; Dongjing Chen^a
• 关键词：Support vector machine ; Nonparallel hyperplanes ; L1-norm loss ; Geometric interpretation ; Matrix inversion
• 刊名：Information Sciences
• 出版年：2016
• 出版时间：1 May 2016
• 年：2016
• 卷：340-341
• 期：Complete
• 页码：86-103
• 全文大小：1064 K

文摘

This paper proposes a novel L₁-norm loss based twin support vector machine (L1LTSVM) classifier for binary recognition. In this L1LTSVM, each optimization problem simultaneously minimizes the L₁-norm based losses for the two classes of points, which results in a different dual problem compared with twin support vector machine (TWSVM). Compared with TWSVM, the main advantages of this L1LTSVM classifier are: first, the dual problems of L1LTSVM do not need to inverse the kernel matrices during the learning process, indicating L1LTSVM not only has a partly sparse decision function, but also can be solved efficiently by some SVM-type learning algorithms, and then is suitable for large scale problems. Second, this L1LTSVM has more perfect and practical geometric interpretation. Experimental results on several synthetic as well as benchmark datasets indicate the significant advantage of L1LTSVM in the generalization performance.